Criminological Research Methods Questions and Answers

Answer: B

For studying habitual drug users, snowball sampling is the most useful method.

Drug users are a hidden population with no list from which to draw a sample, and they are reluctant to come forward. In snowball sampling one begins with a few users who are known and asks them to lead the researcher to others, so the sample grows as the study goes on.

Simple random, cluster and stratified random sampling all need a sampling frame of the whole population, which does not exist for drug users, so they cannot be used in practice.

Answer: C

The chi-square test indicates association.

Chi-square compares the observed frequencies in a cross-table with those expected if the two variables were unrelated. A large value shows that the variables are associated, though not how strongly or in what direction.

It is not a measure of correlation, which needs interval data and a coefficient such as Pearson's r, nor a direct measure of a difference of means, which is the work of a t-test. Significance is what the associated probability value tells, but the thing the statistic reveals is the association.

Answer: C

The partial representation of constructs such as social status, power and intelligence is called a variable.

A construct is an abstract idea that cannot be observed directly. A variable is a measurable aspect of it, such as income or education for social status, so it represents the construct only in part.

Measurement is the process of assigning numbers to variables. An operational definition says how a variable is to be measured, and a definition in general explains a term. The thing that partly represents the construct is the variable.

Answer: C

Chi-square is the technique that can be used to find the relationship between two dichotomous variables.

Two dichotomous variables, such as sex and conviction (yes or no), can be set out in a two-by-two table, and the chi-square test shows whether they are associated.

Regression needs variables that are measured on a scale. Standard deviation and mode are summary measures for one variable and say nothing about the relationship between two.

Answer: B

A statistical index of the strength of the relationship between two variables is the correlation coefficient.

The coefficient, such as Pearson's r, ranges from -1 to +1. Its size shows how strong the relationship is and its sign shows whether it is positive or negative.

Percentage analysis only describes proportions. The t-test compares means, and regression predicts one variable from another and gives an equation and not an index of the strength of the relationship.

Answer: D

The tools for data collection in criminological research are the interview schedule (ii) and the Thematic Apperception Test (iv), which is the combination (ii) and (iv). The interview schedule is a structured list of questions put to a respondent, and the TAT is a projective test in which the subject makes up stories about pictures, which reveal his attitudes and motives.

Alpha error and hypothesis testing are part of statistical analysis, not of the collection of data, so any combination with (i) or (iii) is wrong.

Answer: B

The quota sample is not a random sampling design. It is a non-probability sample in which the interviewer fills quotas for certain categories, such as age or sex, and chooses the persons personally, so not every unit has a known chance of selection.

Simple random, stratified random and cluster samples are all probability sampling designs, in which selection is by chance, so the first, third and fourth options are random designs and are not the answer.

Answer: C

Crime in India is a source of crime data. It is the annual publication of the National Crime Records Bureau, which gives figures on offences reported to the police in the country, state by state.

An administrative report, a handbook of statistics and a census report may contain some figures of the kind, but they are not a source of crime data in the way the yearly report of the Bureau is, which is the one the key accepts.

Answer: B

The standard deviation indicates dispersion, that is, how far the scores in a distribution are spread around the mean. It is the square root of the mean of the squared deviations from the mean.

Association and correlation are the relation between two variables and are measured by coefficients such as chi-square or the correlation coefficient, and significance is judged by tests of hypotheses. None of them is what the standard deviation expresses.

Answer: D

Crime in India is published by the National Crime Records Bureau (printed in the question as National Crime Reports Bureau), which is under the Ministry of Home Affairs and collects and publishes crime statistics of the whole country each year.

The Bureau of Police Research and Development, the National Institute of Criminology and Forensic Science and the National Police Academy are bodies that deal with research, training and forensic science, and they do not publish the annual report.