Understanding the Scientific Method: Hypotheses, Experiments, and Variables, Slides of Process Engineering

Download Understanding the Scientific Method: Hypotheses, Experiments, and Variables and more Slides Process Engineering in PDF only on Docsity!

Scientific method

2

Introduction

 The process by which scientists, collectively and over time, endeavor

to construct an accurate (i.e. reliable, consistent and non-arbitrary)

representation of the world

 Key Attributes

 Objective  Remove personal and cultural biases by focusing on objective testing procedures  Consistent  Hypotheses are usually consistent with broader, currently known scientific laws  In cases where the hypothesis is that one of the broader laws is incorrect or incomplete, the hypothesis should be composed to challenge only one such law at a time  Observable  The hypothesis presented should allow for experiments with observable and measurable results

4

Hypotheses and Predictions

 Hypothesis

 A tentative idea or question that is waiting for evidence to be supported or refuted  Informal hypothesis  Simple question derived from conjecture or observations  e.g. Do males and females differ in their attitudes toward online shopping?  A procedure is developed to collect data  e.g. Conduct a survey of male and female online shoppers  Formal hypothesis  Two or more variables are related to one another  e.g. Use of breadcrumbs in websites can improve user’s efficiency in navigation of the websites  Formulated on the basis of past research findings or theoretical considerations  A study is designed to test the hypothesis  e.g. Participants work on a series of tasks in websites with breadcrumbs or without breadcrumbs, and their task performances are recorded and analyzed

5

Hypotheses and Predictions

 Prediction

 A statement concerning what will occur in a particular investigation  e.g. Participants in websites with breadcrumbs are expected to perform better on the tasks than those in websites without breadcrumbs  If the prediction is confirmed by the results of the study, the hypothesis is supported (not proven); otherwise, the hypothesis is not supported  A variety of methods may be used to test a hypothesis; the more times a hypothesis is supported by studies, the more likely the hypothesis is correct

7

Basic Steps

 Observations and Descriptions

 Curiosity about surroundings  Observe surroundings carefully  Document observations

 Hypothesis Formulation

 Questions are formulated which lead to educated guesses or hypotheses

 Data Collection

 Data collection plan  What, when, where, how many ...?  Experimental or non-experimental methods

 Data Analysis

 Statistical methods are used

8

Basic Steps

 Result Summarization

 Tables, graphics, etc.

 Conclusions and Discussions

 Hypotheses are supported or rejected  Explanations for why certain results were found  Compare with previous similar studies

 Identification of Future Research Needs

 Areas of related interest that should be studied to better understand the subject  Limitations of the study

10

Common Mistakes

 Mistake the hypothesis for an explanation of a phenomenon, without

performing experimental tests

 Temptation of “common sense” and “logic”  e.g. “A picture is worth a thousand words”

 Ignore or rule out data which do not support the hypothesis

 Strong belief in the hypothesis

 Failure to quantitatively estimate systematic errors

 Systematic errors are biases in measurement which lead to measured values being systematically too high or too low  Systematic errors are caused by methods of observation or instrument  Alleged “new discoveries” were later proved to be due to systematic errors

11

Recently, parents and care providers have been encouraged by a technique called “facilitated communication” that seems to allow an autistic child to communicate with others by pressing keys on a keyboard showing letters and other symbols. A facilitator holds the child’s hand to facilitate the child’s ability to determine which key to press. With this technique, many autistic children begin communicating their thoughts and feelings and answer questions posed to them. Many people who see facilitated communication in action regard the technique as a miraculous breakthrough. The conclusion that facilitated communication is effective is based on the comparison of the autistic child’s ability to communicate with and without the facilitator.

Miltenberger and Wittrock (1995) noted that the facilitator might be unintentionally guiding the child’s finger to type meaningful sentences. In other words, the facilitator, rather than the autistic individual, was controlling the communication. This hypothesis was supported in another later study, in which three conditions were examined: 1) the facilitator and child were shown the same pictures; 2) only the child saw the pictures; 3) the facilitator and child were shown different pictures. It turned out that the pictures were correctly identified in only the 1 st^ condition. In the 3 rd condition, the child never made correct responses, and usually the pictures shown to the facilitator were correctly identified

13

It is known that on June 30, 1908 in Tunguska, Siberia, there was an

explosion equivalent to the detonation of about 15 million tons of

TNT. Many hypotheses have been proposed for what caused the

explosion. It is believed that the explosion was caused by a natural

extraterrestrial phenomenon and was not caused by man.

Questions:

1. Is this theory a fact?
2. Is this theory generally accepted to be true, based on evidence to-date?
3. Can this theory be shown to be false and discarded?

Back

14

Variables

 Definition

 An event, situation, behavior, or individual characteristic that varies  e.g. word length, intelligence, etc.

 Categories of Variables

 Situational variables  Characteristics of a situation or environment (e.g. word length, screen size)  Response variables  Responses or behaviors of individuals (e.g. reaction time, task performance)  Participant (subject) variables  Characteristics of individuals (e.g. gender, age)  Mediating variables  Processes that mediate the effects of a situational variable on a particular response  e.g. “Diffusion of responsibility” is used to explain the phenomenon in which helping is less likely when there are more bystanders to an emergency

16

Variables

 Measurement Scales (Cont.)

 Ratio variables  Have all the features of interval scales and have a true zero (e.g. size, weight)  Interval variables and ratio variables are continuous variables  Nominal variables and ordinal variables are categorical variables

17

Nonexperimental Methods

 Make observations or measure the variables of interest as behaviors

occur naturally

 Directly observe behaviors  Ask people to describe their behaviors (e.g. survey)  Examine various public records (e.g. census data)

 A relationship between variables is established when the variables

vary together

 Allows observing covariation between variables (“correlational method”)

19

A study on the effect of the instant messaging in the US Navy’s in-flight missile control showed a significant negative correlation between the chatty factor of an operator and his performance. A person was categorized as chatty if he continued responding to an action communication message ten seconds after notification of a retargeting situation. However, there was not necessarily a cause-and-effort relationship between the two variables, because a third-variable (e.g. mood) could affect both a person’s chatting behavior and task performance

20

Experimental Methods

 Study Cause and Effect

 Use controlled observations and measurements to test hypotheses

 Experimental Control

 All extraneous variables are kept constant  Treat samples in all groups of the experiment identically; the only difference between groups is the manipulated variable of interest

If you design an experiment to compare the effectiveness of two designs of a website, participants in the two designs must have the same technical background related to using websites and be given the same tasks, the lighting and all other relevant conditions will be the same, and so on.